Multi-agent Collaborative Transport on CHAIC Indoor - Low Target 1.0
82TROracle
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Oracleground truth knowledge=true2024.11 | 82 | 0.38 | 0.91 | |
| LLM+BM HelperDecision-making LLM=GPT-4, Behavior Modeling=true2024.11 | 70 | 0.27 | 0.43 | |
| VLM (GPT-4o)Decision-making VLM=GPT-4o2024.11 | 69 | 0.26 | 0.46 | |
| RHP2024.11 | 66 | 0.23 | 0.28 | |
| w/omode=no-helper2024.11 | 51 | — | — | |
| Randomstrategy=random2024.11 | 50 | -0.01 | 0.31 |